AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

BusterNet: Detecting Copy-Move Image Forgery with Source/Target Localization

Yue Wu, Wael Abd-Almageed, Prem Natarajan

ECCV 2018 · Detection and segmentation › Open-set and few-shot detection · approach: Cross-domain translation and pose · 365 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add the manipulation branch (two-branch design, direct training) (ablation)BusterNet · Synthetic 10K test setrecall target: 38.97% -> 47.37%Improved
add the manipulation branch (two-branch design, direct training) (ablation)BusterNet · Synthetic 10K test setrecall source: 32.28% -> 34.12%Improved
add stage-wise training with auxiliary tasks (ablation)BusterNet · Synthetic 10K test setrecall source: 34.12% -> 41.64%Improved
add stage-wise training with auxiliary tasks (ablation)BusterNet · Synthetic 10K test setrecall target: 47.37% -> 53.61%Improved
add stage-wise training with auxiliary tasks (ablation)BusterNet · Synthetic 10K test setaccuracy: 92.74% -> 93.02%Improved
add fusion and end-to-end fine-tuning to the Simi-Det branch (ablation)BusterNet · CASIA CMFDpixel/image AUC: AUC improves by 3-4%Improved
add fusion and end-to-end fine-tuning to the Simi-Det branch (ablation)BusterNet · CASIA CMFDimage-level F-score: 75.85% -> 75.98%Improved
add fusion and end-to-end fine-tuning to the Simi-Det branch (ablation)BusterNet · CASIA CMFDpixel-level F-score (protocol A): 59.16% -> 67.05%Improved
use BusterNet instead of dense-field method [9]copy-move detector · CoMoFoD no attackpixel-level F1 (protocol B, overall): 41.83% -> 49.26%Improved
use BusterNet instead of dense-field method [9]copy-move detector · CoMoFoD no attackF1 on correctly detected subset: 87.82% -> 80.09%Hurt
apply severe JPEG compression (JC1, quality 10) attack (ablation)BusterNet · CoMoFoDcorrectly detected images: 117 -> 60Hurt
restrict source/target scoring to opt-in samplesBusterNet · source/target discernibilityaccuracy: 11.83% -> 77.49%Improved

Later papers that compared with this method

1 later accepted paper reports BusterNet as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy